Sunday 4 December 2011

LECTURE 14(a) – VALIDITY AND RELIABILITY

Validity is the extent to which a test measures what it claims to measure. It is vital for a test to be valid in order for the results to be accurately applied and interpreted (Kendra cherry, 2011).
Validity also refers to the degree to which evidence and theory support the interpretations of test scores entailed by proposed uses of tests (AERA/APA/NCME, 1999).
Validity isn’t determined by a single statistic, but by a body of research that demonstrates the relationship between the test and the behavior it is intended to measure. There are three types of validity:
Category of Validity Definition Example/Non-example
Content validity The extent to which the content of the test matches the instructional objectives. Or in other words the test represent the entire range of possible items the test should cover. A semester or quarter exam that only includes content covered during the last six weeks is not a valid measure of the course's overall objectives -- it has very low content validity.
Criterion-related Validity The extent to which scores on the test are in agreement with other criterion is called concurrent validity. Or to the extent where it can predict an external criterion is called predictive validity. If the SPM trial math tests in Form 5 correlate highly with the SPM math tests, they would have high concurrent validity. The criterion examples are success in school or success in class.
Construct The extent to which an assessment corresponds to other variables, as predicted by some rationale or theory. Or it demonstrates an association between the test scores and the prediction of a theoretical trait. Intelligence tests are one example of measurement instruments that should have construct validity. MUET test is another example because it comprises of reading, writing, listening and speaking test which cover up all the scope needed in mastering a language.

Factors that influence the validity
FACTORS ELABORATION
Reliability A valid test is always reliable because in order to be valid, it need to be reliable in the first place.
Nature of the group consistency of the validity coefficient for subgroups which differ in any characteristic (eg: age, gender, educational level)
Sample heterogeneity A wider range of score results in higher validity coefficient (range restriction phenomenon)
Criterion-predictor relationship There must be a linear relationship between predictor and criterion.
Criterion contamination Get rid of bias by measuring contaminated influences. Then correct this influence statistically by use of partial correlation.
Moderator variables Variable like age, gender, personality characteristics may help to predict performance for particular variables only.

No comments:

Post a Comment